Triple

T4533270
Position Surface form Disambiguated ID Type / Status
Subject Michael Heseltine E106346 entity
Predicate hasSpouse P13 FINISHED
Object Anne Heseltine
Anne Heseltine is the wife of British Conservative politician and former Deputy Prime Minister Michael Heseltine.
E475750 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Anne Heseltine | Statement: [Michael Heseltine, hasSpouse, Anne Heseltine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anne Heseltine
Context triple: [Michael Heseltine, hasSpouse, Anne Heseltine]
  • A. Helen Humes
    Helen Humes was an American jazz and blues singer known for her work with Count Basie’s orchestra and her versatile, swinging vocal style.
  • B. Carobeth Laird
    Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
  • C. Eileen Anketell
    Eileen Anketell was the wife of British television producer, director, and writer Barry Letts, best known for his work on the classic science fiction series "Doctor Who."
  • D. Bronwen Maddox
    Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
  • E. Elizabeth Holdridge
    Elizabeth Holdridge was the wife of American novelist John Dos Passos and a significant companion during his later life and career.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Anne Heseltine
Triple: [Michael Heseltine, hasSpouse, Anne Heseltine]
Generated description
Anne Heseltine is the wife of British Conservative politician and former Deputy Prime Minister Michael Heseltine.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Anne Heseltine
Target entity description: Anne Heseltine is the wife of British Conservative politician and former Deputy Prime Minister Michael Heseltine.
  • A. Helen Humes
    Helen Humes was an American jazz and blues singer known for her work with Count Basie’s orchestra and her versatile, swinging vocal style.
  • B. Carobeth Laird
    Carobeth Laird was an American ethnographer and linguist best known for her influential documentation of Chemehuevi language and culture.
  • C. Eileen Anketell
    Eileen Anketell was the wife of British television producer, director, and writer Barry Letts, best known for his work on the classic science fiction series "Doctor Who."
  • D. Bronwen Maddox
    Bronwen Maddox is a British journalist and policy analyst who has held prominent leadership roles in UK public policy and media organizations.
  • E. Elizabeth Holdridge
    Elizabeth Holdridge was the wife of American novelist John Dos Passos and a significant companion during his later life and career.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69bd43f3d6e08190a91824f833d51bbe completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd57a08ec4819091b84d53d7b564a7 completed March 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69be67b09ed88190b72263c4dd5716b3 completed March 21, 2026, 9:41 a.m.
NEDg Description generation batch_69be682cfe548190b657e0f1694a1142 completed March 21, 2026, 9:43 a.m.
NED2 Entity disambiguation (via description) batch_69be68a634c08190aadfc362199a8d7e completed March 21, 2026, 9:45 a.m.
Created at: March 20, 2026, 1:04 p.m.